Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/marcusgoll/spec-flow/implement-epic-legacygit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/marcusgoll/spec-flow/implement-epic-legacy)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/implement-epic-legacy"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/implement-epic-legacy.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.11956 |
| Opus 5 | $0.00000 | $0.05978 |
| Sonnet 5 | $0.00000 | $0.02391 |
| Haiku 4.5 | $0.00000 | $0.01196 |
Grade C, and why
implement-epic scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`cd ${sprintDir} && rm -rf .next .cache coverage node_modules/.cache` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
execSync( How it starts
The opening of the file, as written. The whole thing — 1,579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement-epic — Parallel Sprint Execution
Current Branch: !git branch --show-current 2>/dev/null || echo "none"
Epic Directory: !ls -d epics/*/ 2>/dev/null | head -1 | xargs basename 2>/dev/null || echo "none"
Worktree Context: !bash .spec-flow/scripts/bash/worktree-context.sh info 2>/dev/null || echo '{"is_worktree": false}'
Worktree Auto-Create: !bash .spec-flow/scripts/utils/load-preferences.sh --key "worktrees.auto_create" --default "true" 2>/dev/null || echo "true"
Sprint Plan: @epics/*/sprint-plan.md
Total Sprints: !grep -c "^## Sprint S" epics/*/sprint-plan.md 2>/dev/null || echo "0"
Execution Layers: !grep -c "^| Layer |" epics/*/sprint-plan.md 2>/dev/null || echo "0"
Locked Contracts: !grep -c "^####.*Contract" epics/*/sprint-plan.md 2>/dev/null || echo "0"
Git Status: !git status --short 2>/dev/null || echo "clean"
Epic Artifacts (after execution):
- @epics//sprints/S/tasks.md (completed tasks per sprint)
- @epics//contracts/.yaml (locked API contracts)
- @epics/*/state.yaml (epic status)
- @epics/*/audit-report.xml (effectiveness metrics)
Parallel sprint execution workflow:
- Detect epic workspace and load sprint-plan.md
- Validate sprint directories, tasks, and contract files
- Execute layers sequentially (sprints within layer run in parallel)
- Launch specialist agents per sprint subsystem
- Monitor progress and consolidate results
- Auto-trigger workflow audit after completion
- Present epic summary with velocity metrics
Key principles:
- Dependency-driven parallelism: Layers execute sequentially, sprints within layer run in parallel
- Contract locking: API contracts locked before implementation to enable parallel work
- Specialist routing: Backend sprints → backend-dev agent, Frontend → frontend-dev, etc.
- True parallel execution: SINGLE message with multiple Task tool calls
- Automatic auditing: Effectiveness metrics captured after implementation
Workflow position: epic → clarify → plan → tasks → implement-epic → optimize → preview → ship
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 1,579 lines · 0 tokens per session scan C 7c81568f6657
implement-epic is a command published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,956 tokens. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
backlog
PitWay: Capture out-of-scope work discovered mid-task, without expanding current scope.
project
Unified project management. Handles detection, initialization, configuration, context generation, and environment loading.
get-to-work
Autonomous ops work. Args: [mode] [repeat]. Modes: tasks | opps | full | escalating (default). Repeat: cycle (keep going, default) | once (single pass). Run this before stepping away from an ops repo.
recap
Summarize what happened in the project since a given date. Produces a short lead on what's different now, backed by tables and lists covering completed work, state changes, backlog movement, and key decisions. Use when the user wants to catch up on project activity, review recent progress, or generate a status update…
whats-next
Generate an executive overview of the project. Synthesizes state, backlogs, and recent plans into a ranked action plan answering "What should we do next?".
sprint-start
Abre uma sprint — cria a branch, o doc da sprint e o objetivo com DoD. Use quando disser "vamos começar a sprint" ou ao terminar a anterior.